Stable Audio, a text-to-music AI tool from Stability AI, once maxed out at 90 seconds. Now, you can generate longer audio content.
Stability AI announced Stable Audio 2.0, an update to Stable Audio 1.0 that lets users generate up to three minutes of AI sound.
StableLM: What to know about Stability AI’s language model
What’s new with Stable Audio 2.0?
As mentioned, Stability AI launched Stable Audio 2.0, an AI audio generator with a free tier. The new model comes with the following new perks:
Mashable Light Speed
With text prompts, users can generate high-quality, full tracks with “coherent musical structure” for up to three minutes long at 44.1 kHz stereo
In addition to text-to-audio, Stability Audio 2.0 now has audio-to-audio capabilities. In other words, you can transform uploaded audio samples via natural language prompts
Stability AI expanded Stable Audio’s sound-effect generation, allowing artists and musicians more “flexibility” and “control”
Stable Audio 2.0 was exclusively trained on a licensed dataset sourced from AudioSparx music library. Opt-out requests from musicians and artists are honored, according to Stability AI, ensuring creators are fairly compensated.
In addition to a Stable Audio 2.0’s free tier, there are also premium subscriptions that offer access to creator licenses and greater monthly allowances for track generation.
Topics
Artificial Intelligence